Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add studioKjm/ai-harness-template --skill supabase-migrationgit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/studiokjm/ai-harness-template/supabase-migration)<a href="https://agentmods.dev/skills/studiokjm/ai-harness-template/supabase-migration"><img src="https://agentmods.dev/badge/skills/studiokjm/ai-harness-template/supabase-migration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/studiokjm/ai-harness-template/supabase-migration"><img src="https://agentmods.dev/badge/skills/studiokjm/ai-harness-template/supabase-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.00499 |
| Opus 5.5 | $0.00033 | $0.00200 |
| Sonnet 5.5 | $0.00016 | $0.00100 |
| Haiku 4.5 | $0.00008 | $0.00050 |
Grade A, and why
supabase-migration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Supabase 마이그레이션 절차
원격(운영/스테이징) DB에는 쓰지 않는다. 모든 검증은 로컬 Supabase에서 한다. 원격 적용은 사용자가 직접, 합의된 절차로 한다.
- 로컬 Supabase 실행 확인:
supabase status(꺼져 있으면supabase start) supabase migration new <snake_case_name>으로 새 파일을 만든다.supabase/migrations/의 기존 파일은 수정·삭제·이름 변경하지 않는다 (check-migrations.sh게이트가 막는다).- SQL 작성 규칙
- 새 테이블은 같은 파일에서
alter table ... enable row level security;와 역할별 정책을 함께 만든다. using (true)/with check (true)정책 금지. 정책은 사용자 역할·소유 조직 기준으로 작성한다.- 정책에서
auth.uid()는(select auth.uid())형태로 감싼다 (initplan 최적화). anon에 불필요한 GRANT를 주지 않는다. SECURITY DEFINER 함수는set search_path = ''.- 정책과 조인에 쓰이는 FK 컬럼에는 인덱스를 만든다.
- 새 테이블은 같은 파일에서
- 검증:
supabase db reset --local(시드까지 적용되는지) 후supabase db advisors --local --fail-on error. 이미 존재하던 오류(baseline)와 이번 변경으로 생긴 오류를 구분해서 보고한다. - 타입 재생성:
supabase gen types typescript --local > <types 경로> - 새 컬럼/테이블이 개발 시드에 필요하면
supabase/seed.sql도 갱신한다. - 보고: 변경 요약, advisors 결과, 원격 적용 시 주의점(기존 화면·권한 영향).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 22 lines · 82 tokens per session scan A b040e05b3465
supabase-migration is a skill published in the GitHub repository studioKjm/ai-harness-template (46 stars, last pushed 21d ago), licensed MIT. It adds 82 tokens to every session and 499 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…
sql-style
Apply the house SQL style guide.
database-migration
Generate, review, test, and deploy database schema migrations. Use when adding columns, creating tables, or changing schema.
staging-deploy
Build, push, migrate, and deploy to staging environment with health check verification. Use when deploying a completed phase to staging.
database-optimization
Query optimization, indexing strategies, and database performance tuning for PostgreSQL and MySQL.
redis-patterns
Redis patterns including caching strategies, pub/sub, streams for event processing, Lua scripts, and data structures.